headroomlabs-ai/headroom
摘要
Headroom 是一个位于 LLM 之前的上下文压缩层,在工具输出、日志、文件和 RAG 片段送入模型前先做压缩,以库、代理和 MCP server 三种形式提供。据项目方数据,编码 agent 可省约 20% token,JSON 类内容可省 60–95% 且答案不变,示例中 55957 token 的 prompt 被压到 24340 token,关键的 FATAL 行仍逐字节保留。适合在意 token 成本或上下文长度上限的 agent 开发者。
相关推荐
xerj-org/xerj
XERJ is the new way for AI to search data. Its autoindex capability activates agents to know your data without the token waste of grep and sed. One command indexes code, docs, logs and PDFs for search, RAG, security audits and agent memory, using 40x fewer tokens than grep. Elasticsearch compatible, so existing clients just work.
Cursor 转 Codex 大半个月,聊聊我的真实感受
Cursor 让我第一次强烈感受到 AI 编程的震撼,Codex 则让我第一次真正感觉到,AI 不只是编程助手,而是一个真正的超级Agent,Codex 明显更接近下一阶段的形态。
mksglu/context-mode
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
JuliusBrussee/caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.